Drug discovery, and much of bioengineering, will progress faster if we are able to engineer molecules to do what we want. Powerful machine learning tools like Evo and Alphafold are emerging to help. It is sometimes unclear how to use these tools in practice or what the components of an end-to-end software system look like in the context of real biology and problems biotechs face in industry. Here we trace the design, build, and testing of viable AAV capsids on a single data platform, LatchBio: 1. Finetuning the genomic language model Evo and generating initial designs 2. Storing molecular libraries in a database accessible to scientists 3. Screening candidates in-silico with batched AlphaFold 4. Processing sequencing data from functional validation assays 5. Synthesizing and visualizing results https://lnkd.in/gmnwjFX3 The design principles generalize to machine learning guided workflows for most biologics. Access to Evo and AlphaFold is provided for public exploration and use. Install this system at your organization, customized to your biology ~ https://latch.bio
Definitely welcome!
Senior Full Stack Engineer
5moAny thoughts on this news? https://www.nature.com/articles/d41586-024-00846-7